Benchmarking interface confidence as a selection criterion for computational nanobody design against survivin's BIR-domain groove
Gately, C.; Guan, X.; Ding, X.
Show abstract
Designed binders are routinely filtered on predicted interface confidence, which reports how self-consistently a model places an interface, not where it lies. We designed 200 nanobody loops against the survivin BIR-domain groove, co-folded 196, and checked epitope contact in every predicted complex. Confidence showed no detectable association with epitope engagement ({rho} = +0.100, 95% CI -0.04 to +0.24, n = 196); its highest and lowest quartiles failed alike (odds ratio 0.97, 95% CI 0.41 to 2.26). It tracked instead the run's other confidence estimates ({rho} = +0.61). Twelve-seed replication separated two candidates the criteria had not: one reached the complete epitope in 10 of 12 runs, the other never. Across 155 predictions the top-ranked model was no better than one drawn at random from its five (P = 0.610), though only 3 of 31 failed on every model. Nothing was assayed; nb_cand_057 is an in silico candidate only.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Evaluation of AlphaFold Antibody-Antigen Modeling with Implications for Improving Predictive Accuracy 92%
- Learning Peptide Recognition Rules for a Low-Specificity Protein 92%
- ExploreTurns: A web tool for the exploration, analysis, and classification of beta turns and structured loops in proteins; application to beta-bulge and Schellman loops, Asx helix caps, beta hairpins and other hydrogen-bonded motifs 92%
Similar papers in this journal
- Novel sampling strategies and a coarse-grained score function for docking homomers, flexible heteromers, and oligosaccharides using Rosetta in CAPRI Rounds 37-45 93%
- The Impact of AI-Based Modeling on the Accuracy of Protein Assembly Prediction: Insights from CASP15 93%
- De novo design of high-affinity antibody variable regions (Fv) against the SARS-CoV-2 spike protein 92%
Similar papers in this journal
- Deep learning assessment of nativeness and pairing likelihood for antibody and nanobody design with AbNatiV2 93%
- AbDesign: Database of point mutants of antibodies with associated structures reveals poor generalization of binding predictions from machine learning models. 92%
- Tuning antibody stability and function by rational designs of framework mutations 92%
Similar papers in this journal
- AlphaFold2 enables accurate deorphanization of ligands to single-pass receptors 92%
- FlowDesign: Improved Design of Antibody CDRs Through Flow Matching and Better Prior Distributions 91%
- DynamicGT: a dynamic-aware geometric transformer model to predict protein binding interfaces in flexible and disordered regions 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.